- IJCAI 2023: Less learn shortcut: Analyzing and mitigating learning of spurious feature-label correlation
- EMNLP 2023 Findings: Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
- BIBM 2024: Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain
- NeurIPS 2024: MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability
- AAAI 2025: Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak
- Arxiv Preprint: GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue
- AAAI 2024: From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery
- AAAI 2024: MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
- Arxiv Preprint: MolFusion: Multimodal Fusion Learning for Molecular Representations via Multi-granularity Views
- Repo: BenTsao: Open-source Chinese Medical Large Language Model
- TKDD: Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Trustworthy Response Generation in Chinese
Research Experience
- Research Center of Social Computing and Information Retrieval (SCIR), Harbin Institute of Technology, Ph.D. student, focusing on the safety and robustness of language models
- Department of Mathematics, The Chinese University of Hong Kong, Research Assistant
Education
- Harbin Institute of Technology, 2021-Now, Ph.D. in Computer Science, Supervisor: Professor Bing Qin and Associate Professor Sendong Zhao
- The Chinese University of Hong Kong, 2024.11-Now, Research Assistant, Department of Mathematics, Supervisor: Professor Fenglei Fan
- Northeastern University, 2017-2021, Bachelor in Computer Science, Supervisor: Associate Professor Feiliang Ren
Background
Currently a Ph.D. student in the Health Intelligence (HI) group of the Social Computing and Information Retrieval (SCIR) research center at Harbin Institute of Technology, supervised by Professor Bing Qin and Associate Professor Sendong Zhao. Research interests lie in the safety and robustness of language models.